arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1810.04700cs.CLcs.AI
收藏

用于数据到文本生成的端到端内容和计划选择

End-to-End Content and Plan Selection for Data-to-Text Generation

Harvard SEAS(哈佛工程与应用科学学院);TTI-Chicago(芝加哥丰田技术研究院);ADAPT(ADAPT中心)

Sebastian Gehrmann, Falcon Z. Dai, Henry Elder, Alexander M. Rush

摘要:

利用神经网络从结构化数据中学习生成流畅的自然语言已成为自然语言生成的常用方法。当结构化数据的形式在示例之间变化时,这个问题可能具有挑战性。本文提出了一个调查的几个扩展序列到序列模型,以考虑潜在的内容选择过程,特别是变异的复制注意和覆盖解码。我们进一步提出了一种基于不同集成的训练方法,以鼓励模型在训练过程中学习不同的句子模板。对这些技术的实证评估显示,在五个自动化指标以及人工评估中,生成的文本质量有所提高。

英文摘要:

Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents a survey of several extensions to sequence-to-sequence models to account for the latent content selection process, particularly variants of copy attention and coverage decoding. We further propose a training method based on diverse ensembling to encourage models to learn distinct sentence templates during training. An empirical evaluation of these techniques shows an increase in the quality of generated text across five automated metrics, as well as human evaluation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑